Smart Healthcare Applications: Detecting DDoS Attacks Efficiently using Hybrid Firefly Algorithm

The rapidly growing and emerging Smart Healthcare Applications (SHA) are reducing the burden on the existing healthcare system caused by limited medical infrastructure and increasing number of diseases. Bio-inspired anomaly-based detection systems are still affected by false positive rates because the approaches are synchronized with user-defined parameters that are unpredictable, resulting in convergence rate, discovery and utilization disparities, algorithm complexity, and unrealistic results. One of the most well-known and effective nature-inspired swarm intelligence metaheuristic algorithms is the Firefly Algorithm (FA). In this work, we propose a Hybridized Firefly Algorithm (HFA) that combines the advantages of the FA and Particle Swarm Optimization (PSO). The bio-inspired HFA is designed to mitigate Distributed Denial-of-Service (DDoS) attacks in SHA. We compare our algorithm with other DDoS attack resistant methods and conclude that our hybrid approach outperforms the existing FAs in terms of accuracy, error prediction, and attack detection time. The statistical results demonstrate the improved accuracy and effectiveness of our proposed HFA model with a higher accuracy of 94.9%, error prediction of 6%, and detection time of 1.12 ms compared to existing DDoS attack detection methods. The proposed HFA methodology is a decentralized architecture, more effective, highly reliable, and available for real-time SHA in terms of monitoring and detecting attacks.